Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    encryption/decryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Table
    -0.07
     Lloyd
    -0.07
    Source
    -0.07
    69
    -0.07
     Title
    -0.07
     table
    -0.07
     Source
    -0.07
    Surface
    -0.07
     staging
    -0.07
    295
    -0.07
    POSITIVE LOGITS
     encryption
    0.08
     Encrypt
    0.08
    encrypt
    0.08
     encrypted
    0.07
     encrypt
    0.07
    Decoder
    0.07
     }
↵
↵
↵
    0.07
    >();
↵
    0.07
    .mongo
    0.07
    .decrypt
    0.07
    Act Density 0.006%

    No Known Activations